cs.AINov 12, 2026

Rational Alignments of Superintelligences via Debates

Authors: Thanawat Sornwanee

Organizations: Stanford University

Abstract

Artificial superintelligences (ASI) is artificial intelligences with greater capability. However, as human principal has to use it, we have to ensure that the agent will perform in the interest of the human. We investigate the framework of ASI-assisted question answering where ASI agents know the correct answer but the human does not. We provide some example of mechanism for rational alignment, where the agent utility is unchanged, but the interaction between the agent and the human principal is controlled to be in a certain fashion. We show specifically that a debate framework where the agents can further reason and behave in a subgame perfect equilibrium manner will lead to a more predictable result, and in some case will be favorable.

Explore similar work

CardsList
  1. Rationalize: Shared Semantic Reasoning for Human-AI Alignment

    May 28, 2026Aritra Dasgupta, Naga Datha Saikiran Battula, Avina Nakarmi +3AI AlignmentHuman-AI Interaction

  2. A Revealed Preference Framework for AI Alignment

    Mar 29, 2026Elchin SuleymanovPreference AlignmentHuman-AI Decision Making